Trees and Ensembles
Decision trees split data with simple questions; random forests and boosting combine many trees into the strongest classic models for tabular data.
Intuition: twenty questions
A decision tree is a flowchart of yes/no questions about the input. Each internal node asks one question about one feature ("is spend <= 3?"). Each leaf gives an answer.
Why people like trees:
- You can read them. A tree is easy to explain to a non-technical person.
- No feature scaling needed: a threshold works the same on rupees and on years.
- They handle mixed feature types and capture interactions (a rule that only applies when two things are true together) without you designing them.
1 of 6